| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0012047285595964158, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.02364279798208e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.02364279798208e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1038.0804, | |
| "eval_samples_per_second": 6.734, | |
| "eval_steps_per_second": 3.367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001204728559596416, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001807092839394624, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 18.3144, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002409457119192832, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00030118213989910396, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030118213989910396, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1049.108, | |
| "eval_samples_per_second": 6.663, | |
| "eval_steps_per_second": 3.331, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003614185678789248, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00042165499585874555, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004818914238385664, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005421278518183872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 24.3082, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1039.0765, | |
| "eval_samples_per_second": 6.727, | |
| "eval_steps_per_second": 3.364, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006626007077780287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007228371357578496, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007830735637376704, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008433099917174911, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009035464196973119, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 42.6719, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009035464196973119, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1043.7115, | |
| "eval_samples_per_second": 6.697, | |
| "eval_steps_per_second": 3.349, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009637828476771327, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010240192756569536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0010842557036367744, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0011444921316165952, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0012047285595964158, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012047285595964158, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1039.4278, | |
| "eval_samples_per_second": 6.725, | |
| "eval_steps_per_second": 3.362, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5915260527575040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |